© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 156901
    Prev
    Next
    INDEX
    Explanations

    men died, very common

    np_acts-logits-general · gemini-2.5-flash-lite

    describing concepts, data, or questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    0.42
    Prepared
    0.41
    Ad
    0.40
     li
    0.40
     إدارة
    0.40
     dovoljno
    0.40
     yönet
    0.39
     nằm
    0.39
    0
    0.37
    Advisor
    0.37
    POSITIVE LOGITS
    asat
    0.51
    atrical
    0.51
     すぎ
    0.50
    igene
    0.49
     variétés
    0.49
     евре
    0.49
    ચ્છ
    0.47
     albumen
    0.47
    ysed
    0.47
    cstring
    0.47
    Activations Density 0.000%

    No Known Activations